VECTOR WIREAI INTELLIGENCE
NVDA$1,847+3.2%MSFT$512+1.1%GOOGL$199-0.4%META$728+2.7%AMD$184-1.2%TSM$212+0.6%PLTR$98+4.1%AI IDX4,821+1.9%
PKT
SEEDRefresh Models Deals Regulatory Sources

Qwen3.6 35B A3B vs Qwen3.7 Plus Preview

AlibabavsAlibaba44 shared benchmarks539 head-to-head
BenchmarkQwen3.6 35B A3BQwen3.7 Plus Preview
AA Agentic Index21.620.8
AA Intelligence32.139.4
AA-LCR66.769
AA-Omniscience-22.22.4
Artificial Analysis Coding Index41.955.9
charxiv_rq7885.9
Claw Eval (pass@3)5062.7
critpt0.39.1
DeepPlanning25.962.3
gdpval27.822.2
GPQA Diamond8690.3
HLE22.235.6
hmmt_feb_202683.692.9
IFBench64.479.1
imo_answer_bench78.986
LiveCodeBench v680.489.6
LVBench71.476.2
MCP Atlas62.873.2
mcpmark3758.7
MLVU86.287.4
mmlu_redux93.394.5
MMLU-Pro85.688.5
MMMU-Pro75.380.5
nl2repo29.441.1
ocrbench_v265.567.1
OmniDocBench 1.589.991.4
OmniScience Accuracy18.822.5
OmniScience Non-Hallucination49.574.5
QwenClawBench52.661.8
RealWorldQA85.386.9
scicode35.851.3
SimpleVQA58.90.8
supergpqa64.771.4
SWE-bench Multilingual67.275.8
SWE-bench Pro49.557.6
SWE-bench Verified73.477.7
TauBench V3 - Banking9.317.9
Terminal-Bench 2.051.570.3
Terminal-Bench 2.144.961
Terminal-Bench Hard34.847
VideoMMMU83.785.4
VITA-Bench35.645.6
τ²-Bench Telecom (AA run)95.393
τ³-Bench67.217.9

Best tracked score per model per benchmark (default configuration; source-attributed). ↓ marks lower-is-better metrics. Open either model for its full surface, provenance and pricing.